Table 2:

AUC values for diagnostic accuracy of 9 radiologists without and with output of ANN

ObserverWithout ANNWith ANNDifferenceP*
Precertification radiologists
    A0.8910.9450.054< .001
    B0.8400.9380.098< .001
    C0.8500.9500.099< .001
    D0.8970.9470.057< .001
Board certified radiologists
    E0.9350.9720.037< .001
    F0.8870.9150.028< .001
    G0.9650.9790.015< .001
    H0.9170.9400.023< .001
    I0.9110.9220.010< .001
Overall average0.8990.9460.047< .001
  • Note:—AUC indicates area under the curve; ANN, artificial neural network;.

  • * Statistically significant with jackknife method by use of DBM MRMC (multiple readers and multiple cases algorithm developed by Metz et al1216).